#rag4 articles

4 articles

AINeutralarXiv – CS AI · 4h ago4

🧠

An Agentic LLM Framework for Adverse Media Screening in AML Compliance

Researchers have developed an agentic LLM framework using Retrieval-Augmented Generation to automate adverse media screening for anti-money laundering compliance in financial institutions. The system addresses high false-positive rates in traditional keyword-based approaches by implementing multi-step web searches and computing Adverse Media Index scores to distinguish between high-risk and low-risk individuals.

AIBullisharXiv – CS AI · 4h ago5

🧠

Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use

Researchers found that simple keyword search within agentic AI frameworks can achieve over 90% of the performance of traditional RAG systems without requiring vector databases. This approach offers a more cost-effective and simpler alternative for AI applications requiring frequent knowledge base updates.

AIBullisharXiv – CS AI · 4h ago3

🧠

Domain-Partitioned Hybrid RAG for Legal Reasoning: Toward Modular and Explainable Legal AI for India

Researchers developed a domain-partitioned hybrid RAG system with knowledge graphs specifically for Indian legal research, combining three specialized pipelines for Supreme Court cases, statutory texts, and penal codes. The system achieved a 70% pass rate on legal questions, nearly doubling the performance of traditional RAG-only approaches at 37.5%.

AIBullisharXiv – CS AI · 4h ago6

🧠

Higress-RAG: A Holistic Optimization Framework for Enterprise Retrieval-Augmented Generation via Dual Hybrid Retrieval, Adaptive Routing, and CRAG

Researchers have developed Higress-RAG, a new enterprise-grade framework that addresses key challenges in Retrieval-Augmented Generation systems including low retrieval precision, hallucination, and high latency. The system introduces innovations like 50ms semantic caching, hybrid retrieval methods, and corrective evaluation to optimize the entire RAG pipeline for production use.

$LINK